Filters








14,361 Hits in 3.1 sec

Fast and effective procedure inlining [chapter]

Oscar Waddell, R. Kent Dybvig
1997 Lecture Notes in Computer Science  
Inlining is an important optimization for programs that use procedural abstraction.  ...  gains in fast linear time.  ...  Conclusion We h a ve presented a procedure inlining algorithm that is both fast and e ective.  ... 
doi:10.1007/bfb0032732 fatcat:ynpbklgcxffhzgoppyw2q3htlu

Dynamic runtime optimization [chapter]

Thomas Kistler
1997 Lecture Notes in Computer Science  
In the second part we give an overview of promising intermodular and profileguided reoptimizations.  ...  In the first part of this paper we argue that dynamic runtime reoptimization will play an important role in future software systems and discuss the requirements for a modular, extensible operating system  ...  Martin Burtscher also developed a prototype algorithm for intermodular inlining upon which some of the presented statistics are based.  ... 
doi:10.1007/3-540-62599-2_30 fatcat:6oqmszgcofh4bfcymxh74vltxa

The effectiveness of flow analysis for inlining

J. Michael Ashley
1997 SIGPLAN notices  
This paper compares four flow analyses to determine how effectively they justify inlining in practice. The paper makes two contributions.  ...  Our measurements show that the effectiveness of the inliner improves slightly as analysis accuracy improves, but the improvement is offset by the compile-time cost of the accurate analyses.  ...  Acknowledgments: We thank Suresh Jagannathan, Andrew Wright, and Marc Feeley for making their benchmarks available.  ... 
doi:10.1145/258949.258959 fatcat:yx6rwx2yivds7bj235m3oxnna4

The effectiveness of flow analysis for inlining

J. Michael Ashley
1997 Proceedings of the second ACM SIGPLAN international conference on Functional programming - ICFP '97  
This paper compares four flow analyses to determine how effectively they justify inlining in practice. The paper makes two contributions.  ...  Our measurements show that the effectiveness of the inliner improves slightly as analysis accuracy improves, but the improvement is offset by the compile-time cost of the accurate analyses.  ...  Acknowledgments: We thank Suresh Jagannathan, Andrew Wright, and Marc Feeley for making their benchmarks available.  ... 
doi:10.1145/258948.258959 dblp:conf/icfp/Ashley97 fatcat:egzpvmybpnhxxjvyvdqf4gzqzq

In or out?

Stephen M Blackburn, Kathryn S McKinley
2002 Proceedings of the third international symposium on Memory management - ISMM '02  
We compare no write barrier, a completely inlined write barrier, an out-of-line write barrier, and a partially inlined barrier (fast path inlined, slow path out-of-line).  ...  Using generational garbage collectors, we study in depth three code placement options for rememberedset write barriers: inlined, out-of-line, and partially inlined (fast path inlined, slow path out-of-line  ...  We also thank Brendon Cahoon, Stephen Fink, David Grove, Michael Hind, Richard Jones, and Eliot Moss for their input and discussions.  ... 
doi:10.1145/512429.512452 fatcat:zqczdloqlnhpdiyryjzy4ecj2q

In or out?

Stephen M Blackburn, Kathryn S. McKinley
2003 SIGPLAN notices  
We compare no write barrier, a completely inlined write barrier, an out-of-line write barrier, and a partially inlined barrier (fast path inlined, slow path out-of-line).  ...  Using generational garbage collectors, we study in depth three code placement options for rememberedset write barriers: inlined, out-of-line, and partially inlined (fast path inlined, slow path out-of-line  ...  We also thank Brendon Cahoon, Stephen Fink, David Grove, Michael Hind, Richard Jones, and Eliot Moss for their input and discussions.  ... 
doi:10.1145/773039.512452 fatcat:qml7qvf3pjcrlgztbov6ofvto4

In or out?

Stephen M Blackburn, Kathryn S McKinley
2002 Proceedings of the third international symposium on Memory management - ISMM '02  
We compare no write barrier, a completely inlined write barrier, an out-of-line write barrier, and a partially inlined barrier (fast path inlined, slow path out-of-line).  ...  Using generational garbage collectors, we study in depth three code placement options for rememberedset write barriers: inlined, out-of-line, and partially inlined (fast path inlined, slow path out-of-line  ...  We also thank Brendon Cahoon, Stephen Fink, David Grove, Michael Hind, Richard Jones, and Eliot Moss for their input and discussions.  ... 
doi:10.1145/512448.512452 fatcat:iac2kakp5rhifewhhbey7vjlq4

Binary analysis for measurement and attribution of program performance

Nathan R. Tallent, John M. Mellor-Crummey, Michael W. Fagan
2009 Proceedings of the 2009 ACM SIGPLAN conference on Programming language design and implementation - PLDI '09  
By combining the recovered static program structure with dynamic calling context information, we can accurately attribute performance metrics to calling contexts, procedures, loops, and inlined instances  ...  of procedures.  ...  We are grateful to Mark Charney and Robert Cohn at Intel for assistance with XED [5] . This work used equipment purchased in part with funds from NSF Grant CNS-0421109.  ... 
doi:10.1145/1542476.1542526 dblp:conf/pldi/TallentMF09 fatcat:2wsfpyttwrfjrhx34fx475rvfm

Binary analysis for measurement and attribution of program performance

Nathan R. Tallent, John M. Mellor-Crummey, Michael W. Fagan
2009 SIGPLAN notices  
By combining the recovered static program structure with dynamic calling context information, we can accurately attribute performance metrics to calling contexts, procedures, loops, and inlined instances  ...  of procedures.  ...  We are grateful to Mark Charney and Robert Cohn at Intel for assistance with XED [5] . This work used equipment purchased in part with funds from NSF Grant CNS-0421109.  ... 
doi:10.1145/1543135.1542526 fatcat:5m62cf7x4fdgfbgnbct7caqpr4

Automatic inline allocation of objects

Julian Dolby
1997 SIGPLAN notices  
It produces performance up to three times as fast as a dynamic model without inlining and roughly equal to that of manually-inlined codes.  ...  Object-oriented languages like Java and Smalltalk provide a uniform object model that simplifies programming by providing a consistent, abstract model of object behavior.  ...  , Vijay Karamcheti, John Plevyak and Xingbin Zhang as well as myself.  ... 
doi:10.1145/258916.258918 fatcat:ktx5yqjhxjaslhvtrscasefctu

Effective Inline-Threaded Interpretation of Java Bytecode Using Preparation Sequences [chapter]

Etienne Gagnon, Laurie Hendren
2003 Lecture Notes in Computer Science  
In this paper, we introduce preparation sequences, a new technique that solves the particular challenge of effectively inline-threading Java.  ...  The dynamic class loading, lazy class initialization, and multi-threading features of Java reduce the effectiveness of a straight-forward implementation of this technique within Java interpreters.  ...  This is particularly effective for sequences of simple instructions, which have a high dispatch to real work ratio. Unfortunately, not all instructions can be inlined.  ... 
doi:10.1007/3-540-36579-6_13 fatcat:36exhvbme5c6ll64plriw47z2m

Automatic inline allocation of objects

Julian Dolby
1997 Proceedings of the ACM SIGPLAN 1997 conference on Programming language design and implementation - PLDI '97  
It produces performance up to three times as fast as a dynamic model without inlining and roughly equal to that of manually-inlined codes. introduction Traditional object-oriented languages (e.g.  ...  Hybrid languages like C++ (111 provide multitudinous lowlevel features (e.g virtual vs non-virtual functions, inline directives, and explicit stack, inline or heap allocation) so programmers can manually  ...  , Vijay Karamcheti, John Plevyak and Xingbin Zhang as well as myself.  ... 
doi:10.1145/258915.258918 dblp:conf/pldi/Dolby97 fatcat:rdeiwcrupjhu5nuwrtdp6niaoy

Optimizing real world applications with GCC Link Time Optimization [article]

T. Glek, J. Hubicka
2010 arXiv   pre-print
In this paper we present overview of the design and implementation of WHOPR and present test results of its behavior when optimizing large applications.  ...  We show main problems seen only when compiling a large application, such as startup time and code size growth.  ...  Acknowledgment We thank to Andi Kleen and Justin Lebar for several remarks and corrections which significantly improved the quality of this paper.  ... 
arXiv:1010.2196v2 fatcat:uqedhulndrhp5pcdcvtyqbkxnm

Interprocedural side-effect analysis in linear time

Keith D. Cooper, Ken Kennedy
2004 SIGPLAN notices  
and function libraries as intrinsic operations in the language, primarily through procedure specialization and inlining.  ...  Hence, ways of reasoning about the side effects of those procedure and function calls were needed.  ... 
doi:10.1145/989393.989418 fatcat:rz5nf5gn75e7be4ac6t3n2lumy

Customization: optimizing compiler technology for SELF, a dynamically-typed object-oriented programming language

C. Chambers, D. Ungar
1989 SIGPLAN notices  
Coupling these new techniques with compiletime message lookup, aggressive procedure inlining, and traditional optimizations has doubled the performance of dynamically-typed object-oriented languages.  ...  The compiler predicts types that are statically unknown but likely, and inserts run-time type tests to verify its predictions.  ...  We also thank Peter Deutsch for many instructive discussions and seminal ideas for the design and implementation of SELF.  ... 
doi:10.1145/74818.74831 fatcat:psndaav6wvgrhccdxbinrolguu
« Previous Showing results 1 — 15 out of 14,361 results